CtrlK
BlogDocsLog inGet started
Tessl Logo

add-connector

Add or update a Sim knowledge base connector for syncing documents from an external source, including auth mode, config fields, pagination, document mapping, tags, and registry wiring. Use when working in `apps/sim/connectors/{service}/` or adding a new external document source.

66

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, project-specific skill whose code templates, invariants, and reference-implementation pointers would let an agent build a connector correctly. Its main costs are redundancy (the meta/runtime split repeated many times) and a monolithic body that inlines selector/tag reference material instead of splitting it into bundle files.

Suggestions

State the client-safe meta / server-runtime split once (in 'Directory Structure') and remove the four or five restatements in 'Connector Structure', the meta.ts closing rule, the API-key example intro, and 'Registering'.

Move the selector-key manifest table and the canonical-pair/deep-dives (rules, examples, dependsOn mapping) into a `references/selectors.md` file, keeping only the pattern summary and link in SKILL.md.

Add an explicit verification step to 'Your Task' and the checklist (e.g., typecheck/build the app and confirm the connector appears in both registries) so the workflow ends with a validation checkpoint.

DimensionReasoningScore

Conciseness

The body is dense with project-specific knowledge (client-safe meta split, canonical pairs, `listingCapped`, content-deferral invariants) that Claude could not know, but the meta/runtime split rule is restated in at least five places ("Directory Structure", "Connector Structure", the `meta.ts` section's closing rule, the API-key example intro, and "Registering"), and code comments repeat adjacent prose (e.g., the `joinTagArray`/`parseTagDate` comments). Not 4: this redundancy goes beyond "minor instances that could be trimmed"; not 2 because the overwhelming majority of tokens carry non-derivable project facts.

3 / 5

Actionability

Guidance is fully concrete: exact file paths, complete `meta.ts`/runtime/registry code templates, concrete `contentHash` format strings with per-service examples (`gdrive:${file.id}:${file.modifiedTime}`), named helper functions, and per-case reference implementations (OAuth/API-key, deferred/inline). Not 4: the templates cover the common cases copy-paste-ready; the `{service}` placeholders are inherent to scaffolding a new connector rather than a gap.

5 / 5

Workflow Clarity

"Your Task" gives a clear 4-step sequence, the "Hard Rule" provides explicit error-recovery branches (ask for samples, implement only documented parts, state unknowns), and a closing checklist verifies every step including auth, selector pairing, registration, and `listingCapped`. Not 5: there is no explicit final verification step (typecheck/build/run the sync) to close the loop; not 3 because the checklist plus fallback paths already function as checkpoints.

4 / 5

Progressive Disclosure

Sections are well-organized with headers and one-level-deep links to repo files (the federated Search README, reference connectors), but there are no bundle reference files at all — the selector-key manifest table, the canonical-pair deep dive, and the tag-definition details are exactly the bulk that belongs in `references/` files, leaving a ~640-line monolith. Not 4: content that should be split is inlined; not 2 because section structure and signaling are present and clear.

3 / 5

Total

15

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states both what the skill does and when to use it in concrete, third-person terms, with a well-scoped path-based trigger that minimizes conflict risk. The only weakness is trigger coverage that could include common service names and synonyms users might mention.

DimensionReasoningScore

Specificity

"Add or update a Sim knowledge base connector for syncing documents from an external source, including auth mode, config fields, pagination, document mapping, tags, and registry wiring" names the domain plus multiple concrete, comprehensive actions covering every part of the task. Not 4: coverage of the skill's components is complete with no gaps; not below since every clause names a concrete action.

5 / 5

Completeness

The "what" is explicit (add/update a connector with auth mode, config fields, pagination, document mapping, tags, registry wiring) and the "when" is explicit ("Use when working in `apps/sim/connectors/{service}/` or adding a new external document source"). Both halves are concrete, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Triggers like "connector", "syncing documents from an external source", "adding a new external document source", and the `apps/sim/connectors/{service}/` path are natural phrases a user would say. Not 5: it omits common synonyms and concrete service names (Confluence, Google Drive, Notion, API key/Bearer token) that would broaden natural triggering.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (Sim knowledge-base connectors) with a path-scoped trigger, making it unlikely to fire for unrelated skills. Not 4: no meaningful overlap risk with other skills' triggers.

5 / 5

Total

19

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (647 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository
simstudioai/sim
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.